US6084858A - Distribution of communication load over multiple paths based upon link utilization - Google Patents

Distribution of communication load over multiple paths based upon link utilization Download PDF

Info

Publication number
US6084858A
US6084858A US08/790,467 US79046797A US6084858A US 6084858 A US6084858 A US 6084858A US 79046797 A US79046797 A US 79046797A US 6084858 A US6084858 A US 6084858A
Authority
US
United States
Prior art keywords
link
path
metric
identified
respective
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Lifetime
Application number
US08/790,467
Inventor
Wallace E. Matthews
Roger Dev
Alex Edward Raj
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Computer Associates Think Inc
Original Assignee
Cabletron Systems Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Cabletron Systems Inc filed Critical Cabletron Systems Inc
Priority to US08/790,467 priority Critical patent/US6084858A/en
Assigned to CABLETRON SYSTEMS, INC. reassignment CABLETRON SYSTEMS, INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: DEV, ROGER, MATTHEWS, WALLACE E.
Application granted granted Critical
Publication of US6084858A publication Critical patent/US6084858A/en
Assigned to APRISMA MANAGEMENT TECHNOLOGIES, INC. reassignment APRISMA MANAGEMENT TECHNOLOGIES, INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: CABLETRON SYSTEMS, INC.
Assigned to FOOTHILL CAPITAL CORPORATION, A CALIFORNIA CORPORATION reassignment FOOTHILL CAPITAL CORPORATION, A CALIFORNIA CORPORATION SECURITY INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: APRISMA MANAGEMENT TECHNOLOGIES, INC., A DELAWARE CORPORATION
Assigned to APRISMA MANAGEMENT TECHNOLOGIES, INC reassignment APRISMA MANAGEMENT TECHNOLOGIES, INC RELEASE OF SECURITY INTEREST RECORDED 10262002 R/F 013447/0331 Assignors: WELLS FARGO FOOTHILL, INC. (FORMERLY KNOWN AS FOOTHILL CAPITAL CORPORATION)
Assigned to CONCORD COMMUNICATIONS, INC. reassignment CONCORD COMMUNICATIONS, INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: APRISMA MANAGEMENT TECHNOLOGIES, INC.
Assigned to COMPUTER ASSOCIATES THINK, INC. reassignment COMPUTER ASSOCIATES THINK, INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: CONCORD COMMUNICATIONS, INC.
Anticipated expiration legal-status Critical
Application status is Expired - Lifetime legal-status Critical

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00Routing or path finding of packets in data switching networks
    • H04L45/12Shortest path evaluation
    • H04L45/124Shortest path evaluation using a combination of metrics
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00Routing or path finding of packets in data switching networks
    • H04L45/12Shortest path evaluation
    • H04L45/125Shortest path evaluation based on throughput or bandwidth

Abstract

A method for selecting a communication path over which to send a communication load between a first station and a second station in a communication network, in which the communication network has a plurality of possible communication paths between the first and second stations. The method comprises identifying at least one of the possible communication paths between the first and second stations, determining a first path metric for each identified path, the first path metric having a value that may vary as distribution of the load across the network varies and selecting one of the at least one identified paths based on the value of the first path metric for each identified path.

Description

BACKGROUND OF THE INVENTION

1. Field of the Invention

This invention relates generally to communications networks, and more particularly to a method of distributing communication loads over multiple alternative paths.

2. Discussion of the Related Art

In an internet, several networks are connected together through the use of gateways and an internetworking protocol. The gateways (often called routers) using the protocol hide the underlying details of the actual networks in order to provide uniform service across the network. TCP/IP is a leading protocol suite for communicating across interconnected networks. "TCP" stands for transmission control protocol, a connection-oriented transport service, while "IP" stands for internet protocol, a connectionless-mode network service.

A connectionless-mode network protocol is typically packet-based. When some entity on the network wishes to send data, it sends that data as a series of packets ("packet" refers to data transmitted in discrete parts, and includes what is known in this art as "packets," "cells," "datagrams" and the like). Associated with each packet is an address indicating where the packet should be delivered. The address may be a unique Media Access Control address ("MAC address") assigned to the station to which the packet will be delivered. An IP packet encapsulates the data and other information necessary to deliver the packet to the IP entity at the destination. The destination IP entity receives the packet, strips off the data, and passes it up to an appropriate upper-layer protocol for processing. See M. Rose "The Simple Book--An Introduction to Management of TCP/IP-Internets," Prentice Hall, 1991.

More recently, there has been a move toward switched networks which provide a connection-oriented service. A discussion of how "virtual connections" may be established in a switched network and how a "best" connection path may be determined is discussed, based on the disclosure in U.S. Pat. No. 5,521,910 which issued May 28, 1996 to W. Matthews, entitled "Network Having Secure Fast Packet Switching And Guaranteed Quality of Service," which is hereby incorporated by reference in its entirety. While the invention is discussed in this context it is not intended to be limiting.

For example, FIG. 1 shows a fully meshed network topology having six Secure Fast Packet Switches (SFPS) labeled S1-S6; each switch is directly connected by a link L (also referred to as an "edge," or "arc"). In FIG. 1, each SFPS switch has four ports: some ports are labeled A for Access, and some are labeled N for Network. Access ports are attached to, for example, end users at a work station, and provide network access security and connection services. Network ports are attached to a communication device which groups a number of users together; these ports need not perform security services since this function has already been performed at the entry (access) port. The end systems, labeled "M-- ", are connected to the switches by links L. One of the end systems M10 is a network management server (NMS) which includes an SFPS switch directory and path server.

The following procedure may be followed when source M11 transmits a packet to destination M99:

1. Access switch S1 receives the packet (from M11) on inbound port A1.

2. S1 looks up in its internal connection table to determine if a valid connection (M11 to M99 mapping) exists.

3. As no connection is yet defined, S1 initiates a message exchange to the SFPS server (M10):

a. Switch S1 sends a message asking if M11 is allowed to talk to M99. This is where security, policy, and administrative constraints are applied.

b. If the two stations M11 and M99 are allowed to have a connection, then the server M10 determines a path of switches to provide a connection between M11 and M99.

c. Since M11 can reach M99 by two different paths, one "best path" is selected. "Best" is determined by, for example, cost, bandwidth, policy, loss and other metrics. A discussion of how this determination may be made is set forth below.

d. Assume the best path chosen traverses S1 to S3 to S5. Server M10 then "programs" each of these switches to support this connection path.

In the above example, the protocol is "transparent" in the M11-M99 interaction--it does not modify the packets being exchanged. In contrast, traditional switches place a connection-identifier in each packet, which is remapped at each switch, to allow the packet to be switched along the path. Here, however, SFPS treats the source medium access control (MAC) address and the destination MAC address, already present in the packet, as a unique "connection-identifier" and thus the packet need not be modified.

In this example, each switch on the path has an internal connection table with the following entries:

______________________________________  SourceSwitch Port    Source MAC Destination MAC                               Out Port______________________________________S1     A1      M11        M99       N2S3     N1      M11        M99       N3S5     N2      M11        M99       A2______________________________________

Once all of the switches are programmed (through, for example, the Simple Network Management Protocol), the packet from M11 destined for M99, i.e.:

______________________________________Destination Address           Source Address                      Data______________________________________M99             M11        Packet date______________________________________ may be "switched" along the path as follows: M11 → A1S1-N2 → N1S3-N3 → N2S5-A2 → M99

Note that once the switches have these connections defined, subsequent packets traverse M11 to M99 without requiring any additional call setup or network management interaction. This provides fast packet switching between the end systems. Note, the M11 to M99 packet exchange occurs as if they were directly connected on the same LAN segment. Thus, a "virtual LAN" is provided, as well as transparent switching.

At each switch on the path, the switch reads from the packet the source and destination MAC addresses and combines them with the inbound (source) port on which the packet is received to form the connection-identifier. If this connection is in the switch's internal connection table, the packet will be forwarded (switched) out of the designated output port according to the corresponding entry in the table. All subsequent M11 to M99 packets will take the same path through the switches. These "virtual connections" exist until they are explicitly removed by the network management system. Thus, once a path is set up, it remains in place regardless of network activity or actual connectivity unless the path is reprogrammed.

Current LAN (local area network) switching technologies do not use link utilization knowledge, or any other metric which varies in response to how the network is being used, to select among alternative paths between pairs of sources and destinations of communication traffic. In a mesh network, the shortest path between a source and destination is the path that involves the fewest number of arcs and nodes between the source and destination. In other words, a path which traverses two nodes is shorter than a path which traverses three nodes. In some instances a fixed cost is assigned to each link. Cost can be any administratively assigned value which helps to differentiate between multiple paths. For example, the cost may be a weighting factor which differentiates between paths based on how long it will take to start a transmission on a particular arc of a path.

Because current strategies use a fixed cost associated with each link, current technologies pick the shortest path or the path with the least cost between a source and destination and continuously use that path for all traffic until some component of that path becomes disabled, and then selects an alternative path. Thus, every connection from source "A" to destination "B" will be routed through the same path. Once the shortest or least costly path is selected, no other alternative paths are considered--for this or any other connection between A and B. The selected path is used over and over again until all of the bandwidth of the path is being used. Alternative paths are ignored until the shortest path is no longer viable. This causes some path components to become congested, and in extreme cases, to fail.

In sum, when the instantaneous load of the network is unbalanced because a majority of the traffic is between a small number of sources and destinations, the network becomes heavily congested along the preferred paths between those sources and destinations. When alternative paths do exist, they are not utilized, and the network operates much less efficiently than it could.

It would thus be desirable to provide a method of distributing a communication load over multiple alternative paths in order to improve network efficiency.

SUMMARY OF THE INVENTION

According to one embodiment of the present invention, a method for selecting a communication path over which to send a communication load is provided. A number of possible communication paths between first and a second stations are identified. A first path metric is then determined for each of the possible paths. The first path metric (for each path) may have a value that varies as the distribution of loads across the network varies. One of the paths is then selected based on the first path metric.

In one embodiment, the first path metric is a function of link metrics for each link in the path. In another embodiment, a second path metric is computed. When a tie among alternative paths is identified based on the first path metric, the second path metric is used to resolve those ties.

According to another embodiment of the present invention, a communication network is provided having a source station, destination station and a plurality of possible communication paths from the source station to the destination station. The network comprises means, responsive to a first distribution of communication loads in the network, for selecting one of the possible communication paths over which to send a first communication load, and means for transmitting the first communication load from the source station to the destination station, based on the selected communication path. In one embodiment, the means for selecting includes means for determining a first path metric for each possible path, and means for selecting one of the possible paths based on the first path metric values.

These and other features and advantages of the present invention shall appear from the following description of certain exemplary embodiments.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a schematic illustration of a mesh network topology with SFPS switches;

FIGS. 2A-2B are flow diagrams illustrating an embodiment of a method according to the present invention; and

FIG. 3 is a block diagram of a computer system in which the present invention may be implemented.

DETAILED DESCRIPTION

As described above, in a connection-oriented network a switch may request a network management server ("NMS") to provide a path for a packet to be sent from the switch (the source) to another switch (the destination) in the network. (Of course, other mechanisms may be used to identify a path between a source and a destination.) Naturally, a number of alternative paths may exist between a source and destination. Accordingly, an efficient and effective method is required for identification and selection of a path from among the possible paths. While the following detailed description is provided with reference to an embodiment of a connection-oriented communication network having an NMS, this is not intended as limiting. The solution is applicable in general to any routing problem in a mesh network such as a communication network, whether or not the network is connection-oriented.

FIG. 2A illustrates one embodiment of a method for a distributing communication load over multiple paths, in accordance with the present invention. First, a set up request for a connection from a source A to a destination B is received (step 14).

At a step 16, potential paths are identified (discussed in greater detail below), and the potential paths are assigned a Metric Z value based on transmission criteria (such as available bandwidth and a current usage count of the path), in step 18. Various methods of determining a Metric Z value are described in greater detail below.

The "best path" is determined based upon each path's Metric Z value(s) (step 18). For example, paths having a higher bandwidth (and thus a lower Metric Z) value may be preferred over paths having a lower bandwidth (and a higher Metric Z value). The path which is determined to be the "best path" is established from the source A to the destination B and is used as the current communication path (step 20). In step 20, the path is established with network components. For switches, this may involve setting the port-to-port mappings, and for routers/gateways, this includes making changes in their routing tables, i.e., whatever path setting mechanism is appropriate to the network element. The usage count (or other metric) of all arcs (links) in the current path is then incremented (or updated) (step 22) and the Metric Z value of the current path is updated to reflect the incremented usage count (or updated metric) (step 24).

Thus, each time a connection is set up between a source and a destination, the best path is selected. If the best path changes after a connection has been set up, e.g., due to setting this connection up or to other changes in distribution of the load across the network, the next connection may be programmed through a different path.

In most cases, it is expected that connections will be programmed for a short period of time before being released (see FIG. 2B). Accordingly, in practice, as connections are set up and released in the network, the communication load across the network will dynamically adjust to a more efficient distribution of load.

Identification of a return path (i.e., destination to source) may be handled separately, i.e., as a separate connection request, or as a part of the same request, i.e. routed, along the same path as the source to destination path.

In an alternative embodiment, a connection is monitored and programmed as the best path shifts, for example, in response to changes in distribution of communication loads in the network. This is more useful where the expected connection set up time is long. Another alternative is for the switch or end station to periodically release and re-request any connections it has--causing the NMS to select the current best path for additional communication.

Referring to the bottom of FIG. 2A, if a connection release request is received (step 26), the usage count (or other metric) of all arcs in the path currently being used is decremented (step 28, FIG. 2B). The path's Metric Z value then is updated in order to reflect the decrease in usage of the path (step 30) and the path is released (step 32).

Identification and Selection of Paths--Best Path Determination

As described above, alternative paths through the network are identified, and a metric is assigned to each (steps 16, 18). A procedure for determining the best path from a source to a destination, given a metric for evaluating the path, will now be discussed.

Determining a "best" path through the switches is important to insuring "fast" transmissions, avoiding bottlenecks, and guaranteeing quality of service. A procedure is described in U.S. Pat. No. 5,521,910, which is hereby incorporated by reference in its entirety.

Of course, to find a best path, the current network topology must be known by the mechanism (e.g., the NMS) designated to assign paths for communication. A number of alternatives may exist, such as those described in U.S. patent application Ser. No. 08/626,596, filed Apr. 2. 1996, which is copending and commonly owned, and hereby incorporated by reference in its entirety. The particular technique used to discover and maintain a representation of the network is not material, however, to the invention described and claimed herein--so long as the information is available to the NMS or other mechanism responsible for identifying the path.

Selection of the best path may be based upon finding a path between any two points in the mesh in which the path is optimal for one or more metrics, where a metric can be any quantifiable property which is used to determine the efficiency of a given path. The problem may also be defined as finding an optimal path through a mesh which satisfies a number of independent constraints. Alternatively, the problem may be defined as finding a path which is optimal for one metric and passes a set of threshold tests for one or more other metrics. Certain metrics are discussed in greater detail below, with reference to the Metric Z computation.

Thus, this method may be thought of, or implemented as, a breadth-first recursive search in parallel. It is initiated at a source node with an initial set of values (one for each metric) and proceeds until there are no further paths to explore. It starts with a list of all the neighbors (neighboring nodes) of the source node. It then processes that list producing another list of all the neighbors of neighbors, etc., until the destination is reached.

As each node is discovered, a traversal value vector is recorded for that node. Each element of the vector corresponds to a current value for one of the metrics. Each node in a model of the network is programmed to be aware of all arcs which originate from it (see U.S. Pat. No. 5,504,921 which describes a model-based network management system). The node reports to the model what the metric values are for the node and the arcs that originate from it. This report from the node is the traversal value vector. Each time a destination node is discovered, a traversal value vector is updated for each node.

As paths are expanded, going from the source node outward (or from the destination node outward, in an alternative embodiment), the metrics are altered in a monotonically increasing or io decreasing function. Monotonically increasing or decreasing metrics are preferred so that the metric increases or remains the same for each traversal or decreases or remains the same)--permitting pruning of possible paths that will not be the best path. Other metrics could, of course, be used.

It can be confusing to describe metrics in terms such as larger, smaller, etc. Therefore, we will use the terms "best, better, worse and worst." For example, a cost metric can be best when it is 0 and worst when it is some maximum positive value. Probability, on the other hand is best when it is 1 and worst when it is 0. Bandwidth is best if its value is a large positive number and worst when it is 0. A metric which is measured in absolute value may be best at 0 or infinity. At initiation, there is a vector of metrics which is applied at the source node. At each traversal of a node or arc (going to the destination) this vector of values is modified and produces a traversal value which accumulates from a best state to a worst state.

The method may use one or more methods of "pruning" to keep the number of potential paths explored from growing too quickly. Examples of pruning include:

When a path discovers a node already within the path, it terminates itself, i.e., further paths are not explored based on this route to that node. This prevents cycles and corresponding infinite loops.

If a path has a corresponding traversal value vector that is not better than a previously identified path (by whatever standard is chosen for selection from among alternative paths), it terminates itself.

Nodes may be initialized with a choke value vector that has "worst case" values for each metric (e.g., infinity for a cost metric, zero for a bandwidth or probability metric). Each time a path reaches that node, if any metric in the path's traversal value vector is better than the corresponding value for the choke value vector, that value is substituted in the node's choke value vector. When a path reaches a node, the path is terminated if no value in the path's traversal value vector is better than any value in the choke value vector--in this circumstance, the path is unlikely to be better than an earlier path that has already reached this node. (Although this rule does not guarantee optimal results where more than one metric is used, an optimal result will be achieved in almost all practical cases).

Any path which would traverse a disabled arc or node terminates itself.

Any path whose traversal value vector fails the filters (threshold value) in any metric, terminates itself.

Any path which encounters an end node (i.e., a node which does not forward traffic, but may be a source or sink for traffic) which is not the destination node, terminates itself.

For each successive traversal list, all the paths going into a single node are grouped together before processing. Any of these paths which is not better than the others in at least one metric is terminated.

With the above pruning steps, only paths which can potentially produce a best result in some metric are allowed to proceed toward the destination. Once there are no more paths to process, all the successful paths are evaluated, and the path which best fits the desired result for presentation is selected. The method of evaluating the paths is described below.

Of course, other implementations of best path searching, such as the well-known Djikstra's Algorithm, may be implemented.

Determination of Metric Z Value

According to one embodiment of the present invention, the metric associated with a path is "dynamic." That is, the metric can vary in response to how the load happens to be distributed across the network.

Usage can be used to provide one such measure. Usage of a link in the network reflects the current communication load on the network. In one embodiment, usage for a link is simply the number of connections programmed/routed through that link. In effect, therefore, each connection is assumed to use the same amount of bandwidth. In another embodiment, usage may be weighted to reflect the communication load for each connection programmed through the applicable link, the weighting based either on measured or anticipated traffic or a figure provided by the station requesting the connection.

The following illustrates the use of dynamic metrics.

In the following embodiments, the "Metric Z" for a path has a primary value and secondary value, and the secondary value is used only to break "ties" between two alternate paths with equal primary Metric Z values. The primary value is the summation of the Metric Z values for each arc e (same as link) in a path I. The primary Metric Z value (Zp) of path I is determined as follows: ##EQU1## where cost(e) is the cost of transmission on each arc e and usage(e) is a usage count of each arc e. Cost may simply be "one" for all arcs, or assigned a greater number if use of an arc is to be discouraged.

Thus, cost, usage and intrinsic bandwidth are metrics associated with an arc--usage being the only dynamic metric. A function of cost, usage and intrinsic bandwidth is computed to provide another (dynamic) metric for the arc. The path metric, Zp (I), is the sum of the arc metrics for each arc in path I. In the best path determination algorithm, therefore, the traversal vector includes a value for metric Zp, which is updated when a new node is visited by adding the arc metric for the applicable arc.

A secondary value (Zs) is determined as the summation of a different set of Metric Z values for each arc e in the path I. The Metric Zs value of a path I is determined as follows: ##EQU2##

As shown in the above equations, Metric Zp and Metric Zs may be determined as a function of the path usage; the bandwidth of the arcs of the path; and an administrative control which establishes a bias for or against the use of specific arcs based on a specific property, such as the cost of use of the arcs. The administrative control is used to weight the Metric Zp and Zs values for each path so that the specific property, such as the cost of use of the path, is one of the determinative factors in deciding which of the paths will be chosen. For example, a first path having a high bandwidth and low usage will not be chosen over a second path having lower bandwidth and/or higher usage if the cost of using the first path renders it less efficient, based on its Metric Z value, than the second path.

In this embodiment, the path with the best aggregate Metric Zp value will be chosen. It may be a path with lower intrinsic bandwidth, but having a ratio of usage-to-bandwidth which is lower than an alternative path with higher intrinsic bandwidth, even when the number of hops (arcs) is greater. If two or more paths have the same aggregate of Metric Zp values, then the path with the minimum aggregate of Metric Zs value will be used. This metric gives a preference for the path with the highest intrinsic bandwidth.

The equations set forth above may be altered in order to stress different characteristics of the paths when determining the best path. The following embodiments (1-3) are variations of the equations disclosed above to determine the Metric Zp value and the Metric Zs value in order to stress different transmission characteristics.

1. If the goal is to avoid paths which may be susceptible to accelerated congestion or decreased available bandwidth, the following functions may be used to assign priority to the available paths:

The primary, Metric Zp value is determined for each path I containing a number of arcs e as follows: ##EQU3## where K is a scaling constant which weights the usage factor in the calculation. A higher value of K decreases the impact of the usage of the path I on the calculation, while a lower value of K increases the impact of the usage of the path I on the calculation. The secondary, Metric Zs value is determined as follows: ##EQU4##

This variation causes fewer connections to be allocated over higher bandwidth paths before lower bandwidth paths are utilized, thereby spreading the load over more paths rather than loading up the higher bandwidth paths.

2. If the particular amount of bandwidth needed is a concern, the primary Metric Zp value may be determined as follows: ##EQU5## where residual-- bandwidth (e)=intrinsic-- bandwidth(e)-used-- bandwidth(e). In some environments, such as SFPS, used-- bandwidth(e) may be an estimated value. In others, such as asynchronous transfer mode, actual data may be available.

In some embodiments, each link may be treated as multiple "pools" of bandwidth. Thus, a 100 MHz channel may be treated as four separate pools of 25 MHz bandwidth. The pools operate in a manner similar to having four separate links, each having a 25 MHz bandwidth. In this case, information in the packet header may be used for selection of the pool to which the packet would be assigned. For example, in ATM networking, the quality of service portion of the header may be used for assignment of the packet to one of multiple pools of bandwidth on a link. In this case, residual, intrinsic and used bandwidth is tracked for each pool.

Each of residual, intrinsic and used bandwidth may be tracked, notwithstanding the fact that tracking all three can be redundant (since the three have a defined relationship). Consider a link using a modem, however. During operation, the speed of the modem may fall, due to a poor telephone connection. In this case, intrinsic bandwidth for the link would also fall. To avoid the possibility of computing a negative residual bandwidth (where intrinsic bandwidth falls below the current used bandwidth), data for each of the three bandwidth measures may be maintained. If the residual bandwidth would otherwise become negative, it may simply be set to zero.

The secondary value Metric Zs is determined as follows: ##EQU6##

This variation is preferable when an estimate of the amount of bandwidth required for a connection is available as it allows a more precise determination of which path is currently the best path to carry the communication load.

3. If the bandwidth ratio is of concern, the primary value Metric Zp may be determined as follows: ##EQU7##

The secondary value Metric Zs is determined as follows: ##EQU8##

As described above, additional metrics may be used. The "best" path may also be determined as some other function of the metrics (e.g., f(Zp,Zs)), or can be made optimal with respect to one metric (or function of more than one metric) while other metrics must meet a minimum threshold criteria.

The above metrics aggregate through simple addition. That is, a path metric is just the sum of each link (arc) metric. Other metrics may aggregate values in a different fashion. For example, to aggregate probability metrics, the metric of each link may be multiplied. Probability metrics that may be usefully employed according to the invention include probability of cell loss or probability of call blocking in asynchronous transfer mode communication networks. Another function for aggregating metrics would be min{ }. For example, a simple bandwidth metric would be aggregated by taking the minimum of the bandwidths of each link on the path. As discussed above, the aggregation function is, preferably, monotonic.

Any of the above embodiments may be implemented in a general purpose computer 190 as shown in FIG. 3. The computer may include a computer processing unit (CPU) 191, memory 192, a processing bus 193 by which the CPU can access the memory 192, and access to a network 194.

The invention may be a computer apparatus which performs the functions of any of the previous embodiments. Alternatively, the invention may be a memory 192, such as a floppy disk, compact disk, or hard drive, which contains a computer program or data structure, for providing to a general purpose computer instructions and data for carrying out the methods. In a preferred embodiment, the computer is part of the Network Management Server, which determines and assigns the "best" paths for each transmission of packets. In another embodiment, the NMS is distributed across the network switches, as described in U.S. patent application 08/626,596, filed Apr. 2, 1996, which is copending and commonly owned, and which is fully incorporated by reference.

The switching technology described herein may be constructed as software and/or hardware including: software objects which exist in embedded devices as firmware; software objects which are part of an application on a commercial computer system; application specific integrated circuits (ASIC), or functionally equivalent hardware components.

Having thus described various embodiments of the invention, further modifications and improvements will readily occur to those skilled in the art and are intended to be within the scope of the invention. Accordingly, the foregoing description is by way of example only, and not intended to be limiting.

Claims (41)

We claim:
1. A method of selecting a communication path over which to send a communication load between a first and a second station in a communication network, the communication network having a plurality of possible communication paths between the first and second stations, the method comprising the steps of:
identifying at least one of the possible communication paths between the first and second stations, wherein each of the at least one identified communication paths includes at least one link in the communication network;
determining a first path metric for each identified path, including:
determining a first link metric for each link of each identified path based on usage, an administrative cost, and an intrinsic bandwidth of the respective link; and
combining the first link metrics for each link of the respective identified path; and
selecting one of the at least one identified paths based on the value of the first path metric for each identified path.
2. The method of claim 1, wherein the first link metric for each link of each identified path is proportional to the administrative cost and the usage of the respective link and inversely proportional to the intrinsic bandwidth of the respective link.
3. The method of claim 1, wherein the first link metric for a link e having an administrative cost, cost(e), a usage, usage(e), and an intrinsic bandwidth, intrinsic-- bandwidth(e), is a function of ##EQU9## .
4. The method of claim 1, wherein the first link metric for a link e having an administrative cost, cost(e), a usage, usage(e), and an intrinsic bandwidth, intrinsic-- bandwidth(e), is a function of ##EQU10## where K is a constant.
5. The method of claim 1, wherein the first link metric for a link e having an administrative cost, cost(e) and a residual bandwidth, residual-- bandwidth(e), is a function of ##EQU11## .
6. The method of claim 1, wherein the first link metric for a link e having an administrative cost, cost(e), a used bandwidth, used-- bandwidth(e), and an intrinsic bandwidth, intrinsic-- bandwidth(e), is a function of ##EQU12## .
7. The method of claim 1, further comprising a step of determining a second path metric for each identified path, and wherein the step of selecting comprises the step of selecting one of the at least one identified paths based on the value of the first path metric and the second path metric for each identified path.
8. The method of claim 7, wherein the second path metric is not dynamic.
9. The method of claim 7, wherein the step of selecting includes the steps of selecting all of the identified paths having an optimal first path metric and, if more than one optimal path is identified, selecting the identified optimal path having the best value for the second path metric.
10. The method of claim 9, wherein each of the at least one identified communication paths includes at least one link in the communication network and wherein:
the first path metric is based on a first link metric for each link in the respective path; and
the second path metric is based on a second link metric for each link in the respective path.
11. The method of claim 10 wherein:
the first link metric is based upon a usage of the respective link and on a bandwidth for the respective link; and
the second link metric is based on a bandwidth of the respective link.
12. A method of transmitting a communication load between a first and a second station in a connection-oriented communication network, the communication network having a plurality of possible communication paths between the first and second stations, the method comprising the steps of:
(a) defining a connection between the first and the second stations, including:
identifying at least one of the possible communication paths between the first and second stations;
calculating a dynamic first path metric for each identified path, the first path metric having a value responsive to changes of the distribution of communication loads across the network; and
selecting one of the at least one identified paths based on the value of the first path metric for each identified path;
(b) transmitting at least a portion of the communication load on the defined connection;
(c) repeating steps (a) and (b) until the transmission of the communications load is complete or the transmission is terminated.
13. The method of claim 12, wherein the step of calculating includes:
determining a first link metric for each link of each identified path; and
combining the first link metrics for each link of the respective identified path.
14. The method of claim 13, wherein the first link metric for each link of each identified path is based on a total number of connections that are currently defined on the network that include the respective link.
15. The method of claim 14, wherein the first link metric for each link of each identified path is further based on an administrative cost and an intrinsic bandwidth of the respective link.
16. The method of claim 14, wherein step (a) further comprises the step of calculating a second path metric for each identified path, and wherein the step of selecting includes the step of selecting all of the identified paths having an optimal first path metric and, if more than one optimal path is identified, selecting the identified optimal path having the best value for the second path metric.
17. An apparatus for transmitting a communication load between a first and a second station in a connection-oriented communication network, the communication network having a plurality of possible communication paths between the first and second stations, the apparatus comprising:
means for defining a connection between the first and second stations, including:
means for identifying at least one of the possible communication paths between the first and second stations;
means for calculating a dynamic first path metric for each identified path, including means for determining a first link metric for each link of each identified path and means for combining the first link metrics for each link of the respective identified path, wherein the first link metric is based on a total number of connections that are currently defined on the network that include the respective link; and
means for selecting one of the at least one identified paths based on the value of the first path metric for each identified path; and
means for transmitting the communication load on the defined connection.
18. The means of claim 17, wherein the first link metric for each link of each identified path is further based on an administrative cost and an intrinsic bandwidth of the respective link.
19. A method of selecting a communication path over which to send a communication load between a first and a second station in a communication network, the communication network having a plurality of possible communication paths between the first and second stations, the method comprising:
identifying at least one of the possible communication paths between the first and second stations;
calculating a dynamic first path metric for each identified path, the first path metric having a value responsive to changes of the distribution of communication loads across the network; and
selecting one of the at least one identified paths based on the value of the first path metric for each identified path.
20. The method of claim 19, wherein each of the at least one identified communication paths includes at least one link in the communication network and the step of calculating includes:
determining a first link metric for each link of each identified path; and
determining the first path metric for each identified path based on the first link metric for each link of the respective identified path.
21. The method of claim 20, wherein the first link metric is based upon a usage of the respective link.
22. The method of claim 21, wherein the first link metric is proportional to the usage of the respective link.
23. The method of claim 21, wherein the first link metric is further based on a bandwidth for the respective link.
24. The method of claim 23, wherein the first link metric is based on a combination of the usage of the respective link and the bandwidth for the respective link.
25. The method of claim 24, wherein the first link metric is proportional to the usage of the respective link and inversely proportional to the bandwidth of the respective link.
26. The method of claim 21, wherein the first link metric is further based on a cost of the respective link.
27. The method of claim 26, wherein the first link metric is based on a combination of the usage and the cost of the respective link.
28. The method of claim 27, wherein the first link metric is proportional to the usage and the cost of the respective link.
29. The method of claim 19, wherein the communications network is connection oriented.
30. An apparatus for selecting a communication path over which to send a communication load between a first and a second station in a communication network, the communication network having a plurality of possible communication paths between the first and second stations, the apparatus comprising:
means for identifying at least one of the possible communication paths between the first and second stations;
means for calculating a dynamic first path metric for each identified path, the first path metric having a value responsive to changes of the distribution of communication loads across the network; and
means for selecting one of the at least one identified paths based on the value of the first path metric for each identified path.
31. The apparatus of claim 30, wherein each of the at least one identified communication paths includes at least one link in the communication network and the means for calculating includes:
means for determining a first link metric for each link of each identified path; and
means for determining the first path metric for each identified path based on the first link metric for each link of the respective identified path.
32. The apparatus of claim 31, wherein the first link metric is based upon a usage of the respective link.
33. The apparatus of claim 32, wherein the first link metric is proportional to the usage of the respective link.
34. The apparatus of claim 32, wherein the first link metric is further based on a bandwidth for the respective link.
35. The apparatus of claim 34, wherein the first link metric is based on a combination of the usage of the respective link and the bandwidth for the respective link.
36. The apparatus of claim 35, wherein the first link metric is proportional to the usage of the respective link and inversely proportional to the bandwidth of the respective link.
37. The apparatus of claim 32, wherein the first link metric is further based on a cost of the respective link.
38. The apparatus of claim 37, wherein the first link metric is based on a combination of the usage and the assigned cost of the respective link.
39. The apparatus of claim 38, wherein the first link metric is proportional to the usage and the assigned cost of the respective link.
40. The apparatus of claim 30, wherein the communications network is connection oriented.
41. The apparatus of claim 30, wherein the apparatus is a network management server.
US08/790,467 1997-01-29 1997-01-29 Distribution of communication load over multiple paths based upon link utilization Expired - Lifetime US6084858A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US08/790,467 US6084858A (en) 1997-01-29 1997-01-29 Distribution of communication load over multiple paths based upon link utilization

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US08/790,467 US6084858A (en) 1997-01-29 1997-01-29 Distribution of communication load over multiple paths based upon link utilization

Publications (1)

Publication Number Publication Date
US6084858A true US6084858A (en) 2000-07-04

Family

ID=25150773

Family Applications (1)

Application Number Title Priority Date Filing Date
US08/790,467 Expired - Lifetime US6084858A (en) 1997-01-29 1997-01-29 Distribution of communication load over multiple paths based upon link utilization

Country Status (1)

Country Link
US (1) US6084858A (en)

Cited By (89)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6195664B1 (en) * 1997-02-21 2001-02-27 Micrografx, Inc. Method and system for controlling the conversion of a file from an input format to an output format
US6240462B1 (en) * 1997-10-14 2001-05-29 At&T System for providing enhanced grade of service for connections over a large network
US6253207B1 (en) * 1997-09-25 2001-06-26 Lucent Technologies Inc. Method and apparatus for transporting multimedia information over heterogeneous wide area networks
US20010045914A1 (en) * 2000-02-25 2001-11-29 Bunker Philip Alan Device and system for providing a wireless high-speed communications network
WO2002015496A1 (en) * 2000-08-11 2002-02-21 Paion Company, Limited Novel switch fabric chipset system and method
US20020023170A1 (en) * 2000-03-02 2002-02-21 Seaman Michael J. Use of active topology protocols, including the spanning tree, for resilient redundant connection of an edge device
US6385172B1 (en) * 1999-03-19 2002-05-07 Lucent Technologies Inc. Administrative weight assignment for enhanced network operation
WO2002046947A1 (en) * 2000-12-04 2002-06-13 Rensselaer Polytechnic Institute System for proactive management of network routing
US6442593B1 (en) * 1999-02-01 2002-08-27 Sony Corporation Methods and apparatus for transmitting prioritized electronic mail messages
US20020159114A1 (en) * 2001-04-17 2002-10-31 Laxman Sahasrabuddhe Method and apparatus for routing signals through an optical network
US20020170002A1 (en) * 2001-03-22 2002-11-14 Steinberg Louis A. Method and system for reducing false alarms in network fault management systems
US6493317B1 (en) * 1998-12-18 2002-12-10 Cisco Technology, Inc. Traffic engineering technique for routing inter-class traffic in a computer network
US20020186665A1 (en) * 2001-03-14 2002-12-12 Donald Chaffee Efficient path learning in network
US20030004674A1 (en) * 2001-06-29 2003-01-02 National Instruments Corporation Shared routing in a measurement system
US20030014462A1 (en) * 2001-06-08 2003-01-16 Bennett Andrew Jonathan Method and system for efficient distribution of network event data
US6526521B1 (en) * 1999-06-18 2003-02-25 Emc Corporation Methods and apparatus for providing data storage access
US20030046390A1 (en) * 2000-05-05 2003-03-06 Scott Ball Systems and methods for construction multi-layer topological models of computer networks
US20030051195A1 (en) * 2000-05-05 2003-03-13 Bosa Patrick A. Systems and methods for isolating faults in computer networks
US20030056140A1 (en) * 2000-05-05 2003-03-20 Taylor David K. Help desk systems and methods for use with communications networks
US6538777B1 (en) * 1998-02-18 2003-03-25 Massachusetts Institute Of Technology Method for establishing connections by allocating links and channels
WO2003027883A1 (en) * 2001-09-26 2003-04-03 Wiltel Communications Group, Inc. Method and apparatus for performance measurement of different network routes between devices
US6560654B1 (en) * 1999-10-12 2003-05-06 Nortel Networks Limited Apparatus and method of maintaining timely topology data within a link state routing network
US6567380B1 (en) * 1999-06-30 2003-05-20 Cisco Technology, Inc. Technique for selective routing updates
US20030128710A1 (en) * 1998-12-28 2003-07-10 Fedyk Donald Wayne Quasi-deterministic gateway selection algorithm for multi-domain source routed networks
US20030137937A1 (en) * 2002-01-22 2003-07-24 Nippon Telegraph And Telephone Corp. Capacity variable link apparatus and capacity variable link setting method
US20030149919A1 (en) * 2000-05-05 2003-08-07 Joseph Greenwald Systems and methods for diagnosing faults in computer networks
US6606482B1 (en) * 2000-09-22 2003-08-12 Mobilnet Corporation Adaptive personal routing in a wireless communication network
US20030172182A1 (en) * 2002-03-05 2003-09-11 Clay Nicholas J. Multi-path content distribution and aggregation
US20030229713A1 (en) * 2002-06-06 2003-12-11 International Business Machines Corporation Server network controller including server-directed packet forwarding and method therefor
US20030229702A1 (en) * 2002-06-06 2003-12-11 International Business Machines Corporation Server network controller including packet forwarding and method therefor
US20040010617A1 (en) * 2002-07-09 2004-01-15 Hitachi, Ltd. Request routing network system, request router apparatus, router apparatus and a method for path setting in a network
US6687229B1 (en) * 1998-11-06 2004-02-03 Lucent Technologies Inc Quality of service based path selection for connection-oriented networks
US6694350B2 (en) * 1998-06-18 2004-02-17 Nec Corporation Information providing system, server, client, information providing method and recording medium
US6697333B1 (en) * 1998-03-04 2004-02-24 Alcatel Canada Inc. Bandwidth load consideration in network route selection
US20040049595A1 (en) * 2001-12-04 2004-03-11 Mingzhou Sun System for proactive management of network routing
US6724733B1 (en) * 1999-11-02 2004-04-20 Sun Microsystems, Inc. Method and apparatus for determining approximate network distances using reference locations
US6724759B1 (en) 2000-08-11 2004-04-20 Paion Company, Limited System, method and article of manufacture for transferring a packet from a port controller to a switch fabric in a switch fabric chipset system
US20040078683A1 (en) * 2000-05-05 2004-04-22 Buia Christhoper A. Systems and methods for managing and analyzing faults in computer networks
US6731631B1 (en) 2000-08-11 2004-05-04 Paion Company, Limited System, method and article of manufacture for updating a switching table in a switch fabric chipset system
WO2004056047A1 (en) * 2002-12-13 2004-07-01 Internap Network Services Corporation Topology aware route control
US6804731B1 (en) 2000-08-11 2004-10-12 Paion Company, Limited System, method and article of manufacture for storing an incoming datagram in switch matrix in a switch fabric chipset system
US20040233859A1 (en) * 2001-05-18 2004-11-25 Martin Daniel J. Method and system for determining network characteristics using routing protocols
US20040264466A1 (en) * 2003-06-25 2004-12-30 Nokia Corporation Bluetooth personal area network routing protocol optimization using connectivity metric
US20050027845A1 (en) * 2000-01-03 2005-02-03 Peter Secor Method and system for event impact analysis
US6868071B1 (en) * 2000-11-15 2005-03-15 Intel Corporation System and method of transmitting data frames in a mesh of data switches
US6920107B1 (en) * 2000-05-24 2005-07-19 Lucent Technologies Inc. Method and apparatus for congestion control for packet-based networks using pipeline reconfiguration
US20050157654A1 (en) * 2000-10-12 2005-07-21 Farrell Craig A. Apparatus and method for automated discovery and monitoring of relationships between network elements
US6947445B1 (en) * 2000-06-09 2005-09-20 Hughes Electronics Corporation Available bandwidth control mechanism
US20050207354A1 (en) * 2002-06-21 2005-09-22 Maziar Nekovee Timer-based feedback in multicast communication
US20050286685A1 (en) * 2001-08-10 2005-12-29 Nikola Vukovljak System and method for testing multiple dial-up points in a communications network
US20060002297A1 (en) * 2004-07-01 2006-01-05 Allan Sand Flow admission control in an IP network
US7082531B1 (en) * 2001-11-30 2006-07-25 Cisco Technology, Inc. Method and apparatus for determining enforcement security devices in a network topology
US7143283B1 (en) * 2002-07-31 2006-11-28 Cisco Technology, Inc. Simplifying the selection of network paths for implementing and managing security policies on a network
US7184402B1 (en) 2001-08-30 2007-02-27 Cisco Technology, Inc Method for multi-link load balancing to improve sequenced delivery of frames at peer end
US20070133420A1 (en) * 2005-10-24 2007-06-14 Tuna Guven Multipath routing optimization for unicast and multicast communication network traffic
US7233571B1 (en) 2001-12-18 2007-06-19 Cisco Technology, Inc. Connection-based bandwidth utilization
US20070140114A1 (en) * 2005-12-20 2007-06-21 Mosko Marc E Method and apparatus for multi-path load balancing using multiple metrics
US20070299954A1 (en) * 2006-06-27 2007-12-27 International Business Machines Corporation System, method and program for determining a network path by which to send a message
US7363368B2 (en) 2001-12-24 2008-04-22 International Business Machines Corporation System and method for transaction recording and playback
US7372811B1 (en) * 2001-08-07 2008-05-13 Cisco Technology, Inc. Load balancing model for multilink frame relay
US20080117892A1 (en) * 2005-01-24 2008-05-22 Nokia Siemens Networks Gmbh & Co. Kg Method for Iterative Routing with the Aid of a Path-Dependent Routing Metric
US7391731B1 (en) 2002-03-07 2008-06-24 Ibasis, Inc. Method for determining best path
US20080162723A1 (en) * 2003-03-05 2008-07-03 Fuyong Zhao Method and apparatus for updating probabilistic network routing information
US20080189225A1 (en) * 2000-11-28 2008-08-07 David Herring Method and System for Predicting Causes of Network Service Outages Using Time Domain Correlation
US7466655B1 (en) * 2003-09-16 2008-12-16 Cisco Technology, Inc. Ant-based method for discovering a network path that satisfies a quality of service equipment
US7471680B1 (en) 2002-06-24 2008-12-30 Cisco Technology, Inc. Method to enhance routing control in PNNI networks
US7480239B1 (en) 2001-11-27 2009-01-20 Cisco Technology, Inc. Method and apparatus for true priority based connection establishment within a PNNI ATM network
US7532574B1 (en) 2003-10-02 2009-05-12 Cisco Technology, Inc. Method and apparatus for improved priority based connection establishment within a PNNI ATM network
US20090204679A1 (en) * 2008-02-07 2009-08-13 Fujitsu Limited Mail management system and mail management method
US20090213846A1 (en) * 2001-11-16 2009-08-27 Ibasis, Inc. SYSTEM AND METHOD FOR VOICE OVER INTERNET PROTOCOL (VoIP) AND FACSIMILE OVER INTERNET PROTOCOL (FoIP) CALLING OVER THE INTERNET
CN100561959C (en) 2003-07-25 2009-11-18 国际商业机器公司 Electronic device connection resource management
US20100054252A1 (en) * 2002-08-20 2010-03-04 Nec Corporation System and method for external resolution of packet transfer information
US7761572B1 (en) * 1999-04-01 2010-07-20 Cisco Technology, Inc. Proximity as an aid to caching and secondary serving of data
US20110002330A1 (en) * 2001-11-16 2011-01-06 Ibasis, Inc. Systems and methods of deciding how to route calls over a voice over internet protocol telephone call routing system
US20110075568A1 (en) * 2009-09-30 2011-03-31 Verizon Patent And Licensing Inc. Resource management in dynamic network environments
US7953888B2 (en) * 1999-06-18 2011-05-31 Level 3 Communications, Llc On-demand overlay routing for computer-based communication networks
US8018953B1 (en) 2003-08-20 2011-09-13 Cisco Technology, Inc. Adaptive, deterministic ant routing approach for updating network routing information
US8103789B1 (en) * 2001-03-01 2012-01-24 Juniper Networks, Inc. Method and apparatus for computing a backup path using fate sharing information
WO2012023067A1 (en) * 2010-08-16 2012-02-23 Telefonaktiebolaget L M Ericsson (Publ) Automated traffic engineering for fat tree networks
US8427958B2 (en) 2010-04-30 2013-04-23 Brocade Communications Systems, Inc. Dynamic latency-based rerouting
US8489720B1 (en) * 2004-03-31 2013-07-16 Blue Coat Systems, Inc. Cost-aware, bandwidth management systems adaptive to network conditions
JP2013150134A (en) * 2012-01-19 2013-08-01 Hitachi Ltd Computer system, virtual server arrangement method, and arrangement control device
US8515959B2 (en) 2000-11-06 2013-08-20 International Business Machines Corporation Method and apparatus for maintaining and navigating a non-hierarchical personal spatial file system
US8848509B2 (en) 2012-04-27 2014-09-30 Telefonaktiebolaget L M Ericsson (Publ) Three stage folded Clos optimization for 802.1aq
US8982689B2 (en) 2012-04-20 2015-03-17 Telefonaktiebolaget L M Ericsson (Publ) Split tiebreakers for 802.1AQ
US9154394B2 (en) 2010-09-28 2015-10-06 Brocade Communications Systems, Inc. Dynamic latency-based rerouting
US20170078186A1 (en) * 2014-03-06 2017-03-16 Telefonaktiebolaget Lm Ericsson (Publ) Routing path selection based on dynamical metric values
US9769070B2 (en) 2015-01-28 2017-09-19 Maxim Basunov System and method of providing a platform for optimizing traffic through a computer network with distributed routing domains interconnected through data center interconnect links
US10003536B2 (en) 2013-07-25 2018-06-19 Grigore Raileanu System and method for managing bandwidth usage rates in a packet-switched network

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5115495A (en) * 1988-10-18 1992-05-19 The Mitre Corporation Communications network system using full-juncture and partial-juncture station status information for alternate-path distance-vector routing
US5233604A (en) * 1992-04-28 1993-08-03 International Business Machines Corporation Methods and apparatus for optimum path selection in packet transmission networks
US5521910A (en) * 1994-01-28 1996-05-28 Cabletron Systems, Inc. Method for determining a best path between two nodes
US5535195A (en) * 1994-05-06 1996-07-09 Motorola, Inc. Method for efficient aggregation of link metrics

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5115495A (en) * 1988-10-18 1992-05-19 The Mitre Corporation Communications network system using full-juncture and partial-juncture station status information for alternate-path distance-vector routing
US5233604A (en) * 1992-04-28 1993-08-03 International Business Machines Corporation Methods and apparatus for optimum path selection in packet transmission networks
US5521910A (en) * 1994-01-28 1996-05-28 Cabletron Systems, Inc. Method for determining a best path between two nodes
US5535195A (en) * 1994-05-06 1996-07-09 Motorola, Inc. Method for efficient aggregation of link metrics

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Ronald O. Brown, "Network Reliability and Availability: Tricky Calculations Mean Managers Frequently Do Not Get What They Need", Manager's Notebook, part 1, pp. 1-5 and part 2, pp. 1-5, Dec. 27, 1995.
Ronald O. Brown, Network Reliability and Availability: Tricky Calculations Mean Managers Frequently Do Not Get What They Need , Manager s Notebook, part 1, pp. 1 5 and part 2, pp. 1 5, Dec. 27, 1995. *

Cited By (135)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6195664B1 (en) * 1997-02-21 2001-02-27 Micrografx, Inc. Method and system for controlling the conversion of a file from an input format to an output format
US6253207B1 (en) * 1997-09-25 2001-06-26 Lucent Technologies Inc. Method and apparatus for transporting multimedia information over heterogeneous wide area networks
US6240462B1 (en) * 1997-10-14 2001-05-29 At&T System for providing enhanced grade of service for connections over a large network
US6538777B1 (en) * 1998-02-18 2003-03-25 Massachusetts Institute Of Technology Method for establishing connections by allocating links and channels
US6697333B1 (en) * 1998-03-04 2004-02-24 Alcatel Canada Inc. Bandwidth load consideration in network route selection
US6694350B2 (en) * 1998-06-18 2004-02-17 Nec Corporation Information providing system, server, client, information providing method and recording medium
US6687229B1 (en) * 1998-11-06 2004-02-03 Lucent Technologies Inc Quality of service based path selection for connection-oriented networks
US6493317B1 (en) * 1998-12-18 2002-12-10 Cisco Technology, Inc. Traffic engineering technique for routing inter-class traffic in a computer network
US6873616B1 (en) * 1998-12-28 2005-03-29 Nortel Networks Limited Quasi-deterministic gateway selection algorithm for multi-domain source routed networks
US20030128710A1 (en) * 1998-12-28 2003-07-10 Fedyk Donald Wayne Quasi-deterministic gateway selection algorithm for multi-domain source routed networks
US7490129B2 (en) 1999-02-01 2009-02-10 Sony Corporation Methods and apparatus for transmitting prioritized electronic mail messages
US6442593B1 (en) * 1999-02-01 2002-08-27 Sony Corporation Methods and apparatus for transmitting prioritized electronic mail messages
US20050091326A1 (en) * 1999-02-01 2005-04-28 Sony Corporation Methods and apparatus for transmitting prioritized electronic mail messages
US6385172B1 (en) * 1999-03-19 2002-05-07 Lucent Technologies Inc. Administrative weight assignment for enhanced network operation
US7761572B1 (en) * 1999-04-01 2010-07-20 Cisco Technology, Inc. Proximity as an aid to caching and secondary serving of data
US7996535B2 (en) 1999-04-01 2011-08-09 Cisco Technology, Inc. Proximity as an aid to caching and secondary serving of data
US20100281111A1 (en) * 1999-04-01 2010-11-04 Cisco Technology, Inc. Proximity as an aid to caching and secondary serving of data
US7953888B2 (en) * 1999-06-18 2011-05-31 Level 3 Communications, Llc On-demand overlay routing for computer-based communication networks
US8599697B2 (en) 1999-06-18 2013-12-03 Level 3 Communications, Llc Overlay network
US6526521B1 (en) * 1999-06-18 2003-02-25 Emc Corporation Methods and apparatus for providing data storage access
US6567380B1 (en) * 1999-06-30 2003-05-20 Cisco Technology, Inc. Technique for selective routing updates
US6560654B1 (en) * 1999-10-12 2003-05-06 Nortel Networks Limited Apparatus and method of maintaining timely topology data within a link state routing network
US6724733B1 (en) * 1999-11-02 2004-04-20 Sun Microsystems, Inc. Method and apparatus for determining approximate network distances using reference locations
US8296412B2 (en) 2000-01-03 2012-10-23 International Business Machines Corporation Method and system for event impact analysis
US20050027845A1 (en) * 2000-01-03 2005-02-03 Peter Secor Method and system for event impact analysis
US20010045914A1 (en) * 2000-02-25 2001-11-29 Bunker Philip Alan Device and system for providing a wireless high-speed communications network
US20020023170A1 (en) * 2000-03-02 2002-02-21 Seaman Michael J. Use of active topology protocols, including the spanning tree, for resilient redundant connection of an edge device
US20030149919A1 (en) * 2000-05-05 2003-08-07 Joseph Greenwald Systems and methods for diagnosing faults in computer networks
US7103807B2 (en) 2000-05-05 2006-09-05 Computer Associates Think, Inc. Systems and methods for isolating faults in computer networks
US7500143B2 (en) 2000-05-05 2009-03-03 Computer Associates Think, Inc. Systems and methods for managing and analyzing faults in computer networks
US7237138B2 (en) 2000-05-05 2007-06-26 Computer Associates Think, Inc. Systems and methods for diagnosing faults in computer networks
US20030056140A1 (en) * 2000-05-05 2003-03-20 Taylor David K. Help desk systems and methods for use with communications networks
US20030046390A1 (en) * 2000-05-05 2003-03-06 Scott Ball Systems and methods for construction multi-layer topological models of computer networks
US20030051195A1 (en) * 2000-05-05 2003-03-13 Bosa Patrick A. Systems and methods for isolating faults in computer networks
US7752024B2 (en) 2000-05-05 2010-07-06 Computer Associates Think, Inc. Systems and methods for constructing multi-layer topological models of computer networks
US7281170B2 (en) 2000-05-05 2007-10-09 Computer Associates Think, Inc. Help desk systems and methods for use with communications networks
US20040078683A1 (en) * 2000-05-05 2004-04-22 Buia Christhoper A. Systems and methods for managing and analyzing faults in computer networks
US6920107B1 (en) * 2000-05-24 2005-07-19 Lucent Technologies Inc. Method and apparatus for congestion control for packet-based networks using pipeline reconfiguration
US6947445B1 (en) * 2000-06-09 2005-09-20 Hughes Electronics Corporation Available bandwidth control mechanism
US6724759B1 (en) 2000-08-11 2004-04-20 Paion Company, Limited System, method and article of manufacture for transferring a packet from a port controller to a switch fabric in a switch fabric chipset system
US6804731B1 (en) 2000-08-11 2004-10-12 Paion Company, Limited System, method and article of manufacture for storing an incoming datagram in switch matrix in a switch fabric chipset system
WO2002015496A1 (en) * 2000-08-11 2002-02-21 Paion Company, Limited Novel switch fabric chipset system and method
US20040095927A1 (en) * 2000-08-11 2004-05-20 You-Sung Chang System, method and article of manufacture for updating a switching table in a switch fabric chipset system
US6731631B1 (en) 2000-08-11 2004-05-04 Paion Company, Limited System, method and article of manufacture for updating a switching table in a switch fabric chipset system
US6606482B1 (en) * 2000-09-22 2003-08-12 Mobilnet Corporation Adaptive personal routing in a wireless communication network
US20050157654A1 (en) * 2000-10-12 2005-07-21 Farrell Craig A. Apparatus and method for automated discovery and monitoring of relationships between network elements
US8515959B2 (en) 2000-11-06 2013-08-20 International Business Machines Corporation Method and apparatus for maintaining and navigating a non-hierarchical personal spatial file system
US8812507B2 (en) 2000-11-06 2014-08-19 International Business Machines Corporation Method and apparatus for maintaining and navigating a non-hierarchical personal spatial file system
US6868071B1 (en) * 2000-11-15 2005-03-15 Intel Corporation System and method of transmitting data frames in a mesh of data switches
US20080189225A1 (en) * 2000-11-28 2008-08-07 David Herring Method and System for Predicting Causes of Network Service Outages Using Time Domain Correlation
US20080215355A1 (en) * 2000-11-28 2008-09-04 David Herring Method and System for Predicting Causes of Network Service Outages Using Time Domain Correlation
WO2002046947A1 (en) * 2000-12-04 2002-06-13 Rensselaer Polytechnic Institute System for proactive management of network routing
US8438308B2 (en) 2001-03-01 2013-05-07 Juniper Networks, Inc. Method and apparatus for computing a backup path using fate-sharing information
US8103789B1 (en) * 2001-03-01 2012-01-24 Juniper Networks, Inc. Method and apparatus for computing a backup path using fate sharing information
US20020186665A1 (en) * 2001-03-14 2002-12-12 Donald Chaffee Efficient path learning in network
US20020170002A1 (en) * 2001-03-22 2002-11-14 Steinberg Louis A. Method and system for reducing false alarms in network fault management systems
US20020159114A1 (en) * 2001-04-17 2002-10-31 Laxman Sahasrabuddhe Method and apparatus for routing signals through an optical network
US20040233859A1 (en) * 2001-05-18 2004-11-25 Martin Daniel J. Method and system for determining network characteristics using routing protocols
US7423979B2 (en) 2001-05-18 2008-09-09 International Business Machines Corporation Method and system for determining network characteristics using routing protocols
US20030014462A1 (en) * 2001-06-08 2003-01-16 Bennett Andrew Jonathan Method and system for efficient distribution of network event data
US7043727B2 (en) 2001-06-08 2006-05-09 Micromuse Ltd. Method and system for efficient distribution of network event data
US7293058B2 (en) * 2001-06-29 2007-11-06 National Instruments Corporation Shared routing in a measurement system
US20030004674A1 (en) * 2001-06-29 2003-01-02 National Instruments Corporation Shared routing in a measurement system
US7372811B1 (en) * 2001-08-07 2008-05-13 Cisco Technology, Inc. Load balancing model for multilink frame relay
US20050286685A1 (en) * 2001-08-10 2005-12-29 Nikola Vukovljak System and method for testing multiple dial-up points in a communications network
US7184402B1 (en) 2001-08-30 2007-02-27 Cisco Technology, Inc Method for multi-link load balancing to improve sequenced delivery of frames at peer end
WO2003027883A1 (en) * 2001-09-26 2003-04-03 Wiltel Communications Group, Inc. Method and apparatus for performance measurement of different network routes between devices
US20090292821A1 (en) * 2001-09-26 2009-11-26 Grib Timothy E Method and apparatus for performance measurement of different network routes between devices
US20090213846A1 (en) * 2001-11-16 2009-08-27 Ibasis, Inc. SYSTEM AND METHOD FOR VOICE OVER INTERNET PROTOCOL (VoIP) AND FACSIMILE OVER INTERNET PROTOCOL (FoIP) CALLING OVER THE INTERNET
US20110002330A1 (en) * 2001-11-16 2011-01-06 Ibasis, Inc. Systems and methods of deciding how to route calls over a voice over internet protocol telephone call routing system
US8351421B2 (en) 2001-11-16 2013-01-08 Ibasis, Inc. System and method for voice over internet protocol (VoIP) and facsimile over internet protocol (FoIP) calling over the internet
US7480239B1 (en) 2001-11-27 2009-01-20 Cisco Technology, Inc. Method and apparatus for true priority based connection establishment within a PNNI ATM network
US7082531B1 (en) * 2001-11-30 2006-07-25 Cisco Technology, Inc. Method and apparatus for determining enforcement security devices in a network topology
US20040049595A1 (en) * 2001-12-04 2004-03-11 Mingzhou Sun System for proactive management of network routing
US7233571B1 (en) 2001-12-18 2007-06-19 Cisco Technology, Inc. Connection-based bandwidth utilization
US7363368B2 (en) 2001-12-24 2008-04-22 International Business Machines Corporation System and method for transaction recording and playback
US20110128848A1 (en) * 2002-01-22 2011-06-02 Nippon Telegraph And Telephone Corporation Capacity variable link apparatus and capacity variable link setting method
US20030137937A1 (en) * 2002-01-22 2003-07-24 Nippon Telegraph And Telephone Corp. Capacity variable link apparatus and capacity variable link setting method
US7912087B2 (en) * 2002-01-22 2011-03-22 Nippon Telegraph And Telephone Corporation Capacity variable link apparatus and capacity variable link setting method
US20030172182A1 (en) * 2002-03-05 2003-09-11 Clay Nicholas J. Multi-path content distribution and aggregation
US7032028B2 (en) * 2002-03-05 2006-04-18 Avica Technology Corporation Multi-path content distribution and aggregation
US7391731B1 (en) 2002-03-07 2008-06-24 Ibasis, Inc. Method for determining best path
US20030229713A1 (en) * 2002-06-06 2003-12-11 International Business Machines Corporation Server network controller including server-directed packet forwarding and method therefor
US20030229702A1 (en) * 2002-06-06 2003-12-11 International Business Machines Corporation Server network controller including packet forwarding and method therefor
US8051213B2 (en) * 2002-06-06 2011-11-01 International Business Machines Corporation Method for server-directed packet forwarding by a network controller based on a packet buffer threshold
US7315896B2 (en) 2002-06-06 2008-01-01 International Business Machines Corporation Server network controller including packet forwarding and method therefor
US7526523B2 (en) * 2002-06-21 2009-04-28 British Telecommunications Public Limited Company Timer-based feedback in multicast communication
US20050207354A1 (en) * 2002-06-21 2005-09-22 Maziar Nekovee Timer-based feedback in multicast communication
US7471680B1 (en) 2002-06-24 2008-12-30 Cisco Technology, Inc. Method to enhance routing control in PNNI networks
US20040010617A1 (en) * 2002-07-09 2004-01-15 Hitachi, Ltd. Request routing network system, request router apparatus, router apparatus and a method for path setting in a network
US7143283B1 (en) * 2002-07-31 2006-11-28 Cisco Technology, Inc. Simplifying the selection of network paths for implementing and managing security policies on a network
US20100054252A1 (en) * 2002-08-20 2010-03-04 Nec Corporation System and method for external resolution of packet transfer information
WO2004056047A1 (en) * 2002-12-13 2004-07-01 Internap Network Services Corporation Topology aware route control
US7584298B2 (en) 2002-12-13 2009-09-01 Internap Network Services Corporation Topology aware route control
US20060182034A1 (en) * 2002-12-13 2006-08-17 Eric Klinker Topology aware route control
US7903650B2 (en) 2003-03-05 2011-03-08 Cisco Technology, Inc. Method and apparatus for updating probabilistic network routing information
US20080162723A1 (en) * 2003-03-05 2008-07-03 Fuyong Zhao Method and apparatus for updating probabilistic network routing information
US20040264466A1 (en) * 2003-06-25 2004-12-30 Nokia Corporation Bluetooth personal area network routing protocol optimization using connectivity metric
US7706282B2 (en) * 2003-06-25 2010-04-27 Leping Huang Bluetooth personal area network routing protocol optimization using connectivity metric
WO2004114568A3 (en) * 2003-06-25 2005-05-19 Leping Huang Bluetooth personal area network routing protocol optimization using connectivity metric
CN100561959C (en) 2003-07-25 2009-11-18 国际商业机器公司 Electronic device connection resource management
US8018953B1 (en) 2003-08-20 2011-09-13 Cisco Technology, Inc. Adaptive, deterministic ant routing approach for updating network routing information
US7466655B1 (en) * 2003-09-16 2008-12-16 Cisco Technology, Inc. Ant-based method for discovering a network path that satisfies a quality of service equipment
US7532574B1 (en) 2003-10-02 2009-05-12 Cisco Technology, Inc. Method and apparatus for improved priority based connection establishment within a PNNI ATM network
US8489720B1 (en) * 2004-03-31 2013-07-16 Blue Coat Systems, Inc. Cost-aware, bandwidth management systems adaptive to network conditions
US20060002297A1 (en) * 2004-07-01 2006-01-05 Allan Sand Flow admission control in an IP network
US8081571B2 (en) 2004-07-01 2011-12-20 Rockstar Bidco, LP Flow admission control in an IP network
US7684322B2 (en) * 2004-07-01 2010-03-23 Nortel Networks Limited Flow admission control in an IP network
US9172648B2 (en) 2004-07-01 2015-10-27 RPX Clearinghouse, LLC Flow admission control in an IP network
US20100177636A1 (en) * 2004-07-01 2010-07-15 Allan Sand Flow Admission Control in an IP Network
US8908509B2 (en) 2004-07-01 2014-12-09 Rockstar Consortium Us Lp Flow admission control in an IP network
US20080117892A1 (en) * 2005-01-24 2008-05-22 Nokia Siemens Networks Gmbh & Co. Kg Method for Iterative Routing with the Aid of a Path-Dependent Routing Metric
US20070133420A1 (en) * 2005-10-24 2007-06-14 Tuna Guven Multipath routing optimization for unicast and multicast communication network traffic
US20070140114A1 (en) * 2005-12-20 2007-06-21 Mosko Marc E Method and apparatus for multi-path load balancing using multiple metrics
US7492717B2 (en) * 2005-12-20 2009-02-17 Palo Alto Research Center Incorporated Method and apparatus for multi-path load balancing using multiple metrics
US9137043B2 (en) * 2006-06-27 2015-09-15 International Business Machines Corporation System, method and program for determining a network path by which to send a message
US20070299954A1 (en) * 2006-06-27 2007-12-27 International Business Machines Corporation System, method and program for determining a network path by which to send a message
US20090204679A1 (en) * 2008-02-07 2009-08-13 Fujitsu Limited Mail management system and mail management method
US9100304B2 (en) * 2009-09-30 2015-08-04 Verizon Patent And Licensing Inc. Resource management in dynamic network environments
US20110075568A1 (en) * 2009-09-30 2011-03-31 Verizon Patent And Licensing Inc. Resource management in dynamic network environments
US20140059186A1 (en) * 2009-09-30 2014-02-27 Verizon Patent And Licensing Inc. Resource management in dynamic network environments
US8576728B2 (en) * 2009-09-30 2013-11-05 Verizon Patent And Licensing Inc. Resource management in dynamic network environments
US8427958B2 (en) 2010-04-30 2013-04-23 Brocade Communications Systems, Inc. Dynamic latency-based rerouting
AU2011290494B2 (en) * 2010-08-16 2014-12-11 Telefonaktiebolaget L M Ericsson (Publ) Automated traffic engineering for fat tree networks
US9210071B2 (en) 2010-08-16 2015-12-08 Telefonaktiebolaget L M Ericsson (Publ) Automated traffic engineering for fat tree networks
CN103026668A (en) * 2010-08-16 2013-04-03 瑞典爱立信有限公司 Automated traffic engineering for fat tree networks
WO2012023067A1 (en) * 2010-08-16 2012-02-23 Telefonaktiebolaget L M Ericsson (Publ) Automated traffic engineering for fat tree networks
US9154394B2 (en) 2010-09-28 2015-10-06 Brocade Communications Systems, Inc. Dynamic latency-based rerouting
JP2013150134A (en) * 2012-01-19 2013-08-01 Hitachi Ltd Computer system, virtual server arrangement method, and arrangement control device
US8982689B2 (en) 2012-04-20 2015-03-17 Telefonaktiebolaget L M Ericsson (Publ) Split tiebreakers for 802.1AQ
US8848509B2 (en) 2012-04-27 2014-09-30 Telefonaktiebolaget L M Ericsson (Publ) Three stage folded Clos optimization for 802.1aq
US10003536B2 (en) 2013-07-25 2018-06-19 Grigore Raileanu System and method for managing bandwidth usage rates in a packet-switched network
US20170078186A1 (en) * 2014-03-06 2017-03-16 Telefonaktiebolaget Lm Ericsson (Publ) Routing path selection based on dynamical metric values
US10110467B2 (en) * 2014-03-06 2018-10-23 Telefonaktiebolaget Lm Ericsson (Publ) Routing path selection based on dynamical metric values
US9769070B2 (en) 2015-01-28 2017-09-19 Maxim Basunov System and method of providing a platform for optimizing traffic through a computer network with distributed routing domains interconnected through data center interconnect links

Similar Documents

Publication Publication Date Title
Ma et al. Routing high-bandwidth traffic in max-min fair share networks
Wang et al. An overview of routing optimization for internet traffic engineering
Chen et al. An overview of quality of service routing for next-generation high-speed networks: problems and solutions
US6819654B2 (en) Trunking inter-switch links
US6842463B1 (en) Automated and adaptive management of bandwidth capacity in telecommunications networks
US6253230B1 (en) Distributed scalable device for selecting a server from a server cluster and a switched path to the selected server
Fortz et al. Robust optimization of OSPF/IS-IS weights
US8625420B2 (en) System and method for increasing granularity of prefix control in a computer network
US7948899B2 (en) Method and apparatus for communications traffic engineering
EP1601143B1 (en) Efficient and robust routing independent of traffic pattern variability
US6333918B1 (en) Method of forming routing data
US7619982B2 (en) Active probe path management
JP5138847B2 (en) Network system, network relay device, network relay monitoring device, and network operation method
US6778531B1 (en) Multicast routing with service-level guarantees between ingress egress-points in a packet network
US6538991B1 (en) Constraint-based routing between ingress-egress points in a packet network
US6038212A (en) Method and system for optimizing the connection set up time in high speed communication networks for recovering from network failure
EP0568477B1 (en) Method and apparatus for optimum path selection in packet transmission networks
US7046665B1 (en) Provisional IP-aware virtual paths over networks
US6822940B1 (en) Method and apparatus for adapting enforcement of network quality of service policies based on feedback about network conditions
EP1303944B1 (en) Multi-path dynamic routing algorithm
CA2424680C (en) Method and apparatus for the assessment and optimization of network traffic
US6904017B1 (en) Method and apparatus to provide centralized call admission control and load balancing for a voice-over-IP network
Iyer et al. An approach to alleviate link overload as observed on an IP backbone
US6584071B1 (en) Routing with service level guarantees between ingress-egress points in a packet network
US7336613B2 (en) Method and apparatus for the assessment and optimization of network traffic

Legal Events

Date Code Title Description
AS Assignment

Owner name: CABLETRON SYSTEMS, INC., NEW HAMPSHIRE

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:MATTHEWS, WALLACE E.;DEV, ROGER;REEL/FRAME:008893/0158;SIGNING DATES FROM 19970617 TO 19970623

STCF Information on status: patent grant

Free format text: PATENTED CASE

AS Assignment

Owner name: APRISMA MANAGEMENT TECHNOLOGIES, INC., NEW HAMPSHI

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:CABLETRON SYSTEMS, INC.;REEL/FRAME:011590/0363

Effective date: 20000929

Owner name: APRISMA MANAGEMENT TECHNOLOGIES, INC.,NEW HAMPSHIR

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:CABLETRON SYSTEMS, INC.;REEL/FRAME:011590/0363

Effective date: 20000929

AS Assignment

Owner name: FOOTHILL CAPITAL CORPORATION, A CALIFORNIA CORPORA

Free format text: SECURITY INTEREST;ASSIGNOR:APRISMA MANAGEMENT TECHNOLOGIES, INC., A DELAWARE CORPORATION;REEL/FRAME:013447/0331

Effective date: 20021014

FPAY Fee payment

Year of fee payment: 4

AS Assignment

Owner name: APRISMA MANAGEMENT TECHNOLOGIES, INC, NEW HAMPSHIR

Free format text: RELEASE OF SECURITY INTEREST RECORDED 10262002 R/F 013447/0331;ASSIGNOR:WELLS FARGO FOOTHILL, INC. (FORMERLY KNOWN AS FOOTHILL CAPITAL CORPORATION);REEL/FRAME:018668/0833

Effective date: 20050222

Owner name: APRISMA MANAGEMENT TECHNOLOGIES, INC,NEW HAMPSHIRE

Free format text: RELEASE OF SECURITY INTEREST RECORDED 10262002 R/F 013447/0331;ASSIGNOR:WELLS FARGO FOOTHILL, INC. (FORMERLY KNOWN AS FOOTHILL CAPITAL CORPORATION);REEL/FRAME:018668/0833

Effective date: 20050222

AS Assignment

Owner name: CONCORD COMMUNICATIONS, INC., MASSACHUSETTS

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:APRISMA MANAGEMENT TECHNOLOGIES, INC.;REEL/FRAME:019028/0320

Effective date: 20070208

Owner name: CONCORD COMMUNICATIONS, INC.,MASSACHUSETTS

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:APRISMA MANAGEMENT TECHNOLOGIES, INC.;REEL/FRAME:019028/0320

Effective date: 20070208

AS Assignment

Owner name: COMPUTER ASSOCIATES THINK, INC., NEW YORK

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:CONCORD COMMUNICATIONS, INC.;REEL/FRAME:019047/0414

Effective date: 20070208

Owner name: COMPUTER ASSOCIATES THINK, INC.,NEW YORK

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:CONCORD COMMUNICATIONS, INC.;REEL/FRAME:019047/0414

Effective date: 20070208

FPAY Fee payment

Year of fee payment: 8

FPAY Fee payment

Year of fee payment: 12